Voice-Powered Medical Visualization
An intelligent holographic display that responds to voice commands, rendering real-time 3D anatomical models through a 100 cm LED fan — bridging AI and medical education.
Explore the Project →HoloMed AI combines a locally-running large language model (Ollama) with a high-resolution holographic LED fan to create an interactive medical education platform. Students and educators can query anatomical structures using natural speech and receive immersive 3D visual responses.
The system integrates real-time speech recognition, AI-driven dialogue, and controlled hardware to deliver a seamless, touchless experience — purpose-built for the modern medical classroom.
Speak naturally to query the system. Real-time speech-to-text powered by Python SpeechRecognition enables hands-free operation in clinical and classroom environments.
An Ollama-based LLM processes queries locally — no cloud dependency — providing accurate, context-aware responses about anatomy, physiology, and medical concepts.
A 100 cm LED persistence-of-vision fan renders high-resolution 3D anatomical animations, creating a floating hologram visible without special glasses or screens.
Text-to-speech output via gTTS / pyttsx3 delivers spoken responses in sync with visual display, creating a fully multimodal interactive experience.